Dynamic detection of abnormalities in video analysis of crowd behavior with DBSCAN and neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Advances in Science, Technology and Engineering Systems Journal Year : 2020

Dynamic detection of abnormalities in video analysis of crowd behavior with DBSCAN and neural networks

Acheli Dalila
  • Function : Author
Kesraoui Mohamed
  • Function : Author

Abstract

Visual analysis of human behavior is a broad field within computer vision. In this field of work, we are interested in dynamic methods in the analysis of crowd behavior which consist in detecting the abnormal entities in a group in a dense scene. These scenes are characterized by the presence of a great number of people in the camera’s field of vision. The major problem is the development of an autonomous approach for the management of a great number of anomalies which is almost impossible to carry out by human operators. We present in this paper a new approach for the detection of dynamic anomalies of very dense scenes measuring the speed of both the individuals and the whole group. The various anomalies are detected by dynamically switching between two approaches: An artificial neural network (ANN) for the management of group anomalies of people, and a DensityBased Spatial Clustering of Application with Noise (DBSCAN) in the case of entities. For greater robustness and effectiveness, we introduced two routines that serve to eliminate the shades and the management of occlusions. The two latter phases have proven that the results of the simulation are comparable to existing work.
No file

Dates and versions

hal-02561478 , version 1 (04-05-2020)

Identifiers

  • HAL Id : hal-02561478 , version 1

Cite

Hocine Chebi, Acheli Dalila, Kesraoui Mohamed. Dynamic detection of abnormalities in video analysis of crowd behavior with DBSCAN and neural networks. Advances in Science, Technology and Engineering Systems Journal, 2020, 1 (5), pp.56-63. ⟨hal-02561478⟩
360 View
0 Download

Share

Gmail Facebook X LinkedIn More